EP2689650A1 - Lernender autonomer Rasenmäher - Google Patents
Lernender autonomer Rasenmäher Download PDFInfo
- Publication number
- EP2689650A1 EP2689650A1 EP12178244.5A EP12178244A EP2689650A1 EP 2689650 A1 EP2689650 A1 EP 2689650A1 EP 12178244 A EP12178244 A EP 12178244A EP 2689650 A1 EP2689650 A1 EP 2689650A1
- Authority
- EP
- European Patent Office
- Prior art keywords
- mower
- obstacle
- lawn mower
- robotic lawn
- user
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000012549 training Methods 0.000 claims description 28
- 230000006399 behavior Effects 0.000 claims description 20
- 238000000034 method Methods 0.000 claims description 15
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 230000011664 signaling Effects 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract description 14
- 238000001514 detection method Methods 0.000 abstract description 12
- 230000003993 interaction Effects 0.000 abstract description 8
- 230000007246 mechanism Effects 0.000 abstract description 3
- 244000025254 Cannabis sativa Species 0.000 description 14
- 238000013459 approach Methods 0.000 description 3
- 238000012790 confirmation Methods 0.000 description 3
- 240000001949 Taraxacum officinale Species 0.000 description 2
- 235000005187 Taraxacum officinale ssp. officinale Nutrition 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005672 electromagnetic field Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 244000260524 Chrysanthemum balsamita Species 0.000 description 1
- 235000005633 Chrysanthemum balsamita Nutrition 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241001520823 Zoysia Species 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000003466 anti-cipated effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005352 clarification Methods 0.000 description 1
- 230000009849 deactivation Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000003278 mimic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D34/00—Mowers; Mowing apparatus of harvesters
- A01D34/006—Control or measuring arrangements
- A01D34/008—Control or measuring arrangements for automated or remotely controlled operation
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01D—HARVESTING; MOWING
- A01D75/00—Accessories for harvesters or mowers
- A01D75/18—Safety devices for parts of the machines
- A01D75/185—Avoiding collisions with obstacles
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/96—Management of image or video recognition tasks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
Definitions
- the present invention is directed to a robotic lawn mower and a training method thereof.
- the robotic lawn mower can detect and identify obstacles and can autonomously avoid the detected obstacles while operating.
- the robotic lawn mower is able to be trained, in order to learn new obstacles for improving its visual obstacle detection.
- a profound user-mower interaction enables a user to customize the robotic lawn mower.
- bump and sonar sensors work reliably only for large obstacles. Flat obstacles like smart phones or hoses are not recognized, and may be damaged when the mower drives over them. This drawback can potentially be removed by attaching a camera on the mower and recognizing obstacles by means of image processing.
- One typical solution in this respect is to provide a classifier module of the mower with samples of grass and obstacles so that the classifier module is able to distinguish between drivable grass and non-drivable obstacles.
- EP 2 286 653 describes an autonomous lawn mower that combines camera grass recognition with the output of a grass sensor.
- the grass sensor is used to bootstrap and update a classifier that classifies pixels either as grass or non-grass based on their pixel values (e.g. color).
- a computer implementation for controlling a mower with a camera is described.
- the classifier of the mower cannot in any way be influenced by a user.
- the mower can also not recognize different classes of obstacles, and consequently cannot trigger different behaviors of the mower regarding different obstacles.
- WO 2010/077198 describes an autonomous robotic lawn mower and a method for establishing a wireless communication link between the lawn mower and a user.
- a border-wire-based robotic mower is disclosed and is able to communicate with a cellular network structure.
- the mower can inform the user when the mower detects a "situation".
- the user can send back an acknowledgement signal or a message.
- no information for clarification of an uncertain detection result or for improving a classifier installed in the mower software is mentioned.
- the user is not able to improve the classifier, and also different obstacles cannot trigger different behaviors of the mower.
- US 6611738 B2 describes a general purpose mobile device, whose navigation is based on GPS.
- a movement teach-in is disclosed based on the GPS data, where a teach-in is a well-known technique in the field of robotics for teaching a robot to mimic a certain sequence of motor commands or motor positions by moving a robot manually or by means of a remote control.
- the user can give additional information about the working area, like the position of a newly planted tree.
- training and improving of the mower's visual obstacle detection by the user is not possible.
- US 2010/0324731 A1 describes a method for establishing a desired area of confinement for an autonomous robot, and an autonomous robot implementing a control system for executing the same.
- An already known method of movement teach-in for acquiring a user-defined perimeter is described.
- an interaction between a user and the mower via a smart phone is disclosed.
- a map generated by means of perimeter information can be displayed on the smart phone.
- the mower may be remotely controlled via the smart phone.
- the base station may act as a communication gateway between smart phone and mower.
- interactions concerning the visual recognition of the mower are not anticipated.
- the smart device cannot display the visual input of the mower, so that the user cannot give any input for updating a classifier.
- WO 2011/002512 describes visual grass recognition based on image statistics.
- One idea is that the statistics in a current camera image are compared to the statistics of grass that were recorded in advance. This is a typical example of a predefined detection, which cannot solve the problems addressed by the present invention, because each garden has its own individual properties.
- the target of this invention is to improve the state-of-the-art in view of the above-described drawbacks.
- a particular aim of the present invention is to develop an autonomous lawn mower that is able to adapt its visual obstacle recognition based on user input.
- the user can adapt a pre-trained classifier module in the mower, which is used for identifying obstacles on the lawn.
- the user can separate obstacles into different classes, and can assign different behaviors of the autonomous lawn mower to these classes.
- the classifier module is trained with types of obstacles that may be encountered during operation at a specific environment (e.g. garden).
- a specific environment e.g. garden
- this basic classifier module can then be adapted and edited ("customized") by the user to the needs of a specific environment (e.g. garden). By doing so the problem of foreseeing all possible obstacles is strongly reduced.
- the basic set of obstacles plus the user-defined obstacle set is in total still smaller than a general obstacle set, and thus can be handled well by state-of-the-art classifier modules.
- the thus customized classifier module of the present invention has to remember only a small set of obstacles that is specific for a certain garden, it is possible to provide more detailed obstacle recognition. Instead of detecting objects only as obstacles or grass, it is possible to distinguish different objects as different obstacles. This enables the user to put different obstacles into different classes. Each class of obstacles can then e.g. trigger a certain behavior of the lawn mower. For example, the user might want daisy flowers to be spared by the mower, but dandelions to be cut by the mower. Another case could be that the user wants to be informed, if the mower sees an unknown person.
- Another advantageous aspect of the user feedback is to improve the obstacle detection of the mower in cases where the classifier module cannot make a reliable decision.
- the mower can e.g. send a sample image to the user, who in response informs the mower, whether the object is an obstacle, can be cut or should be spared.
- the present invention is directed to a robotic lawn mower comprising at least one camera for obtaining an input image, a memory for storing information about obstacles, a classifier module of a computing unit connected to the memory, for segmenting obstacles within the input image supplied from the camera and identifying segmented obstacles based on the information stored in the memory, and a control unit for controlling a movement of the mower based on the identification of at least one obstacle, wherein the classifier module is provided with an interface in order to edit the information stored in the memory upon acceptance of user input.
- New obstacles are obstacles, for which no corresponding information is yet stored in the memory.
- Information about obstacles in the memory can also be changed or deleted.
- the classifier module of the robotic lawn mower can thus be fine-tuned by the user through training the mower in the garden.
- the classifier module Due to the possible customization through user input, the classifier module has to remember only a small set of obstacles, which are specifically selected for the user's garden, and thus more detailed obstacle recognition is possible. Further, instead of simply detecting objects in a garden as either obstacles or grass, it is possible to identify, and thus to distinguish and classify, different obstacles. Thus, the user is also able to customize the behavior of the robotic mower depending on the type or class of one or more identified obstacles, or on specific characteristics like shape, size or color of an identified obstacle, whereby a more flexible usage of the mower is achieved.
- the classifier module is configured to edit the information stored in the memory according to segmented obstacles within the input image. For example, when a segmented obstacle within the input image cannot be identified by the classifier module based on the information stored in the memory, the user can teach the classifier module the unknown obstacle. In the simplest case the user inputs a confirmation that the unknown segmented obstacle is a valid obstacle that should be learned. In this case the interface can e.g. be a single confirmation button on the mower. In this way the classifier module can be customized.
- the robotic lawn mower is adapted to be selectively in a training mode, wherein in the training mode the classifier module is configured to automatically start editing the information stored in the memory, if an obstacle is positioned in the field of view of the at least one camera.
- the user can give input to enter the training mode.
- the user can press a training mode button on the mower, or can send a message to the mower via a wireless communication channel that triggers the training mode.
- the training mode the user can edit the information in the memory of the mower in a simple and fast manner.
- the classifier module is configured to estimate the position of the obstacle in the field of view of the camera by using a segmentation algorithm that separates foreground pixels from background pixels.
- the same segmentation algorithm can also be used during the normal mowing operation for identifying segmented obstacles.
- Known state of the art segmentation algorithms can be employed.
- the robotic lawn mower is provided with mowing blades and is configured to drive forward with its mowing blades switched off, until the mower hits the obstacle, in order to estimate the position of the obstacle, or until the obstacle is beneath the mower, in order to estimate the maximal height of the obstacle.
- the control unit of the mower is adapted to control the above behavior, and can further calculate the position and/or height of one or more detected obstacles.
- a more accurate definition of the obstacles can be obtained and stored as information in the memory. Further, classification of obstacles is possible.
- the robotic lawn mower is configured to send a message containing a snapshot image taken by the at least one camera to a remote smart device preferably using a wireless channel, and receive information about an annotated snapshot image from the smart device as user input.
- the snapshot image is a still image obtained from the input image of the at least one camera.
- the user can annotate the image on the remote smart device, in order to provide information about an obstacle.
- the classifier module of the mower can then analyze and interpret the annotation it receives from the user, and can learn and classify the obstacle in the snapshot image. For learning the obstacle, the classifier module stores information about the segmented obstacle in the memory. Obstacle recognition by the classifier module can in this way be easily customized and fine-tuned, also during the normal operation of the mower.
- the robotic lawn mower is configured to send the message to the remote smart device, when the classifier module has segmented an obstacle within the input image, which it cannot identify, or when a confidence value of the obstacle identification is below a given threshold.
- the message can request a user input via the remote smart device, e.g. a confirmation that a specific action is to be taken by the mower or a simple yes/no decision for determining whether the segmented object is indeed an obstacle that is to be learned. In this way both the obstacle identification and the behavior of the mower can be improved and customized.
- the robotic lawn mower is configured to receive a user notification as user input, and to determine from the user notification, whether the snapshot image contains an obstacle or not. That means the user notifies the mower, whether the snapshot contains an obstacle or not.
- the mower can in this way learn new obstacles during its normal operation, and can immediately adapt its mowing behavior to the newly learned obstacles.
- the robotic lawn mower is configured to determine from the fact that a user has added a contour around an object in the snapshot image that said object is an obstacle.
- the user can e.g. draw the contour around the obstacle on his remote smart device, and can then send this information back to the mower.
- the mower can interpret the contour as an indication of an obstacle, can segment the obstacle precisely based on the contour, and can store the obtained information about the obstacle in the memory.
- the robotic lawn mower is configured to obtain additional information about an obstacle from at least one tag received together with the user notification.
- the tags with additional information can be provided by the user.
- the tags can be saved in addition to the other obstacle information in the memory.
- the tags are helpful information for identifying and/or classifying obstacles.
- the at least one tag is an obstacle class.
- Obstacle classes can e.g. be used to trigger a common behavior of the mower.
- control unit is configured to control different behaviors of the mower according to different received obstacle tags.
- the user can assign different behaviors of the mower according to his preference.
- a used defined behavior can be carried out.
- the different behaviors include evading the obstacle, driving over the obstacle, taking a snapshot of the obstacle, and signaling an acoustic alarm.
- the robotic lawn mower is configured to communicate with the remote smart device via a data server and a client software.
- the data server is located in a charging station of the mower.
- the client software is software installed on the remote smart device.
- the data server is adapted to buffer messages in a queue for performing an asynchronous communication between the mower and the smart device. That means, the messages are collected and stored in the data server, so that the user can answer all messages at once at a later point in time. Thus, the usage of the mower becomes more convenient for the user, since the user is not annoyed by frequently incoming messages.
- the robotic lawn mower is configured to receive a control instruction from the remote smart device.
- the mower i.e. its behavior, can be controlled remotely via the remote smart device of the user.
- the robotic lawn mower is configured to send a live stream of the input image of the at least one camera to the remote smart device.
- the user can thereby customize the mower in real-time.
- the remote smart device is a remote telecommunications smart device like a PDA, a smart phone or a tablet, or another remote smart device, preferably capable of communicating in a wireless manner, like a PC, an intelligent house control unit or an external control unit for the mower.
- the present invention is further directed to a method for training a robotic lawn mower comprising a classifier module of a computing unit for segmenting obstacles within an input image supplied from at least one camera and identifying segmented obstacles based on the information stored in a memory (10), wherein the method for training comprises providing user input via an interface of the classifier module in order to edit the information stored in the memory.
- Providing user input can, for example, be carried out by setting the mower into a training mode (e.g. by pressing a training mode button) and positioning the mower in front of an obstacle (so that the obstacle is in the field of view of a camera of the mower).
- a training mode e.g. by pressing a training mode button
- user input can be provided via a remote smart device, preferably through a wireless communication interface.
- the user input can be provided in response to a request or a snapshot image from the mower, or initiatively.
- the figures show an autonomous or robotic lawn mower 1 capable of visual obstacle detection and thus having the capacity to detect a wide range of different obstacles 3, which are otherwise hard to detect with the typically used sensors, e.g. bump sensors and/or sonar sensors.
- the typically used sensors e.g. bump sensors and/or sonar sensors.
- flat mobile phones or hoses are prone to be driven over by the mower, thereby damaging these objects as well as the mower blades.
- a common way for visual obstacle detection is to use a learning or classifier module 3 (see Fig. 1 ) that is implemented in a computing unit 11 of the lawn mower.
- This classifier module 3 is trained with pre-set information prior to the delivery of the mower to the user, and is thus able to detect obstacles 6 that appear in the visual input images of at least one camera 2 of the mower 1, which camera 2 supplies an output signal to the computing unit of the lawn mower.
- the pre-set information about the obstacles 6 is stored in a memory 10 of the mower 1.
- the memory 10 can also be part of the classifier module 3, and can e.g. be at least one solid state memory, a hard drive or similar storage device.
- the classifier module 3 is functionally connected to the memory 10, in order to identify obstacles 6 based on the stored information and on the output signal 9 of the at least one camera 2. It can further send a scene classification signal 12 to a (movement) control unit 4 of the mower 1, which then uses the information about the scene and the obstacle 6 for a certain action, e.g. to avoid an obstacle 6.
- this invention proposes that the user of the mower 1 can train the classifier module 3 to the specific properties of a garden, i.e. the user can customize and improve the obstacle identification capabilities of the mower 1.
- the classifier module 3 of the mower 1 of the present invention is provided with an interface, in order to edit the information about obstacles stored in the memory upon acceptance of user input.
- the information in the memory 10 is edited by the classifier module 3 according to segmented obstacles 6 within the input image 9, which cannot be identified by the classifier module 3.
- the computing unit 11 of the mower can, for example, be selectively set by the user into a training mode, in which the classifier module 3 can learn new obstacles 6 and store additional information about the new obstacles 6 for later use in its memory 10.
- Fig. 1 shows a schematic illustration of the mower 1 of the present invention.
- the mower 1 has at least one camera 2, which obtains a camera image (input image) 9.
- the mower 1 can also be equipped with more than one camera 2, and objects can be detected either from multiple input images 9, or the input images 9 of the cameras 2 can be switched.
- the camera 2 can be any kind of optical camera (e.g. visible light camera, infrared camera or the like).
- the mower 1 can also be equipped with different kinds of cameras 2.
- side or back cameras 2 are also useful.
- the at least one camera 2 feeds an output signal (i.e. a generated input image 9) into a classifier module 3 of the mower 1.
- the classifier module may be implemented into the software of the mower 1.
- the classifier module 3 can store information about obstacles in the memory 10, and can segment, detect and identify obstacles 6 from the input image 9 of the at least one camera 2.
- known segmentation algorithms can be used, e.g. algorithms separating foreground pixels from background pixels.
- the segmented obstacles can be identified based on the stored information (which can e.g. be shape, dimensions, size, volume, contours, color, brightness or the like).
- the classifier module 3 can further output a scene classification signal 12 to a control unit 4.
- the classification signal 12 can indicate identified obstacles 6, which can also be classified.
- identified obstacles 6 can be put into classes (e.g. plants, people, objects, animals etc.) either automatically based on the information stored in the memory 10, or by a specific user input.
- the classifier module 3 can also take into account the input of one or more sensors 5 (like a bump, sonar or gyro sensor) for a more accurate identification and classification of obstacles 6.
- the classifier module has an interface 13 for receiving the user input, in order to edit the information in the memory 10.
- the control unit 4 is able to control the behavior, in particular the movement, of the mower 1. That means it can at least cause the mower 1 to drive (forwards and backwards) and steer (turn left or right). Further, it may cause activation or deactivation of mowing blades of the mower 1, may vary the movement speed of the mower 1, or change other mower 1 or even camera 2 parameters (e.g. exposure, aperture, shutter speed, hue, zoom etc.).
- the control unit 4 can be realized by a microprocessor or a similar device.
- the control unit 4 can be further connected to one or more sensors 5, like bump sensor, sonar sensor, gyro sensor or the like. The control unit 4 can take into account all the information it receives (i.e.
- the input signals from the one or more sensors 5, and the output signal 12 from the classifier module 3 can control the operation of the mower 1 based or in accordance with the received information.
- the behavior of the mower 1 can thus be controlled depending on an identified obstacle 6 or a class of obstacles 6.
- the most basic idea of the present invention in respect to editing the information in the memory 10 is that the user sets a training mode of the mower 1, e.g. by pressing a training mode button or sending a training mode command from a remote smart device. Then the user positions an obstacle 6 that is to be newly learned in front of the mower 1, in particular in the field of view of at least one of the cameras 2 (or alternatively positions the mower 1 in front of the obstacle 6, in case the obstacle is immobile like a flower bed or a tree).
- the classifier module 3 can automatically trigger a learning mechanism, e.g. if an obstacle 6 is positioned in the field of view of the camera 2, in which it starts editing the information in the memory. In this scenario the classifier module 3 tries to segment the obstacle 6 within the input image 9, and then uses this segmentation to learn possibly all parameters describing the new obstacle 6. This information about the newly learned obstacle 6 is then stored in the memory 10. Thus, the information in the memory is edited.
- the mower 1 can send an input image 9 (or a snapshot or scene data taken from the input image 9) from the at least one camera 2 to a data sever 7 that can further connect to a client software running on a remote smart device 8 (e.g. a remote smart telecommunications device like a smart phone, PDA or tablet, or a PC or other processing unit) of the user.
- a remote smart device 8 e.g. a remote smart telecommunications device like a smart phone, PDA or tablet, or a PC or other processing unit
- the user can provide a precise segmentation of the obstacle 6 as user input to the mower 1.
- the user can draw a contour (see Fig. 4 ) around the obstacle 6 of interest in the image that has been sent by the mower 1.
- This added contour can then be sent back from the remote smart device 8 to the data sever 7 of the mower 1, which receives and provides this information further to the classifier module 3. Since the classifier module 3 of the mower 1 now has precise information on which pixels of the snapshot image show the obstacle 6 to be learned, the learning procedure is much more effective and faster when compared to the case where the classification module 3 has to estimate on its own where exactly the obstacle 6 is located within the input image of the camera 2.
- the user can provide, in addition or alternatively to the contour provided in the snapshot image, more information about the obstacle 6.
- This further information can e.g. be provided in the form of tags (see Fig. 5 ).
- the obstacle 6 could be assigned via a tag to a class like "nice flower” or "bad flower”.
- the mower 1 is adapted to receive the tag set by the user, to store them in the memory 10 in relation to the obstacle information, and to interpret the tag, in order to obtain the class information.
- the class information can be used to train the classifier module 3, e.g. to distinguish different kinds of obstacles 6.
- the tags could also concern the size, shape or color or the like of an obstacle 6.
- Different kinds or characteristics of obstacles 6 can be used to trigger different behaviors of the mower 1, which are controlled by the control unit 4.
- the user could put dandelions in a "bad flower” class. When the mower 1 encounters such an obstacle 6, it will try to remove it by mowing it. Other obstacles 6 could be spared, so that only specific flowers or plants are mowed.
- the user-mower interaction described above needs not necessarily be triggered by the user (see Fig. 6 ).
- the mower 1 When the mower 1 is operating in the user's garden, it might encounter (at a time t) an obstacle 6, which the classifier module 3 cannot identify, or for which a confidence value of obstacle identification is below a threshold value.
- the threshold value can be set and adjusted via user input.
- the classifier module 3 is not sure what kind of obstacle it sees, or whether the object is an obstacle 6 at all.
- the mower 1 can take and send an image or a snapshot of the current situation (i.e. the current input image 9 of the camera 2) to the remote smart device 8 of the user, who can then resolve the situation by telling the mower 1 what it has encountered.
- a further idea of the present invention is to queue the mower requests in the data server 7. That means that (at a time t) when the mower 1 encounters an unknown object, the mower 1 sends the snapshot image to the data server 7. The mower continues working, while for the time being avoiding the unknown object.
- the snapshot is stored in the data server 7,
- the user When the user has time (e.g. at a time point t+Dt 1 ) he can check, whether the data server 7 has collected new notifications, and can download the data at once. The user can then process the data, e.g. by annotating or tagging the snapshot, and send the annotated or tagged snapshot back to the data sever 7 (or the mower 1).
- the mower 1, in particular the classifier module 3 receives the annotations and tags from the data server 7 (or directly from the user), and the mower 1 can immediately use the information to adapt the classifier module 3 and the behavior of the mower 1.
- the mower 1 can continue to work on the formerly unknown objects, since it now knows how to handle them.
- the mower 1 will regard the queued instances as obstacles 6, and will not drive over these. This enables a natural and asymmetric user-mower interaction, which neither hampers the mower 1 during its operation, nor does it annoy the users.
- the core of this invention is a profound user-mower interaction, which enables the user to teach a robotic lawn mower 1 for improving its visual obstacle detection.
- the main idea of the invention is that the user can show some typical obstacles 6 from his garden to the mower 1. This will increases the performance of the visual obstacle detection.
- the user just places the mower 1 in front of an obstacle 6, and activates the learning mechanism of the classifier module 3 of the mower 1, which then edits information about obstacles 6 stored in a memory 10.
- remote smart devices 8 such as smart phones or tablets
- the mower can send the input image 9 to the smart device 8, and the user can provide a detailed annotation of the image. This will drastically improve the learning, because the mower 1 is provided with ground truth information.
- a further extension to this idea is to tag objects, i.e. obstacles, and to relate certain activities of the mower 1 to the tag, like informing the user.
- the mower 1 could also initiate an interaction by requesting annotation or tag information for unknown or hard to classify objects. The mower 1 then uses this annotation for adapting its classifier 3.
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Environmental Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Electromagnetism (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Harvester Elements (AREA)
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP12178244.5A EP2689650B1 (de) | 2012-07-27 | 2012-07-27 | Lernender autonomer Rasenmäher |
US13/951,504 US9137943B2 (en) | 2012-07-27 | 2013-07-26 | Trainable autonomous lawn mower |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP12178244.5A EP2689650B1 (de) | 2012-07-27 | 2012-07-27 | Lernender autonomer Rasenmäher |
Publications (2)
Publication Number | Publication Date |
---|---|
EP2689650A1 true EP2689650A1 (de) | 2014-01-29 |
EP2689650B1 EP2689650B1 (de) | 2014-09-10 |
Family
ID=46727104
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
EP12178244.5A Active EP2689650B1 (de) | 2012-07-27 | 2012-07-27 | Lernender autonomer Rasenmäher |
Country Status (2)
Country | Link |
---|---|
US (1) | US9137943B2 (de) |
EP (1) | EP2689650B1 (de) |
Cited By (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104904404A (zh) * | 2014-03-14 | 2015-09-16 | 宝时得机械(中国)有限公司 | 智能割草机 |
EP2939513A1 (de) * | 2014-04-30 | 2015-11-04 | LG Electronics Inc. | Rasenmäherroboter und Steuerungsverfahren dafür |
WO2016055159A3 (de) * | 2014-10-11 | 2016-07-14 | Audi Ag | Verfahren zum betrieb eines automatisiert geführten, fahrerlosen kraftfahrzeugs und überwachungssystem |
CN105922257A (zh) * | 2016-04-28 | 2016-09-07 | 纳博特南京科技有限公司 | 一种基于移动电子设备的机器人示教*** |
CN107006229A (zh) * | 2017-03-30 | 2017-08-04 | 江苏科技大学 | 一种坐骑式割草机翻滚保护装置及其保护方法 |
EP3298874A1 (de) | 2016-09-22 | 2018-03-28 | Honda Research Institute Europe GmbH | Robotergartenarbeitsvorrichtung und verfahren zur steuerung davon |
EP3234839A4 (de) * | 2014-12-16 | 2018-08-29 | iRobot Corporation | Systeme und verfahren zur bilderfassung und kommentierung des erfassten bildes mit informationen |
DE102014015493B4 (de) | 2014-10-06 | 2019-04-18 | Audi Ag | Verfahren zum Betrieb eines Kraftfahrzeugs und Kraftfahrzeug |
IT201800010737A1 (it) * | 2018-11-30 | 2020-05-30 | Volta Robots S R L | Metodo di controllo di un mezzo di lavorazione del terreno sulla base di elaborazioni d’immagini perfezionato e relativo sistema |
IT201800020182A1 (it) * | 2018-12-19 | 2020-06-19 | Fabrizio Bernini | Robot tagliaerba |
EP3670109A3 (de) * | 2018-12-18 | 2020-07-15 | Samsung Electronics Co., Ltd. | Verfahren und vorrichtung zur steuerung des verhaltens eines dienstroboters |
CN112659124A (zh) * | 2020-12-14 | 2021-04-16 | 南昌大学 | 一种基于Android***的虚拟仿真与控制*** |
CN112684785A (zh) * | 2019-10-18 | 2021-04-20 | 南京德朔实业有限公司 | 自行走割草***和户外行走设备 |
GB2588614A (en) * | 2019-10-29 | 2021-05-05 | Samsung Electronics Co Ltd | Method and system for customising a machine learning model |
CN112818806A (zh) * | 2021-01-27 | 2021-05-18 | 国网四川省电力公司电力科学研究院 | 一种基于深度学习的变电站巡检机器人辅助导航方法 |
KR20210059839A (ko) * | 2019-11-15 | 2021-05-26 | 동의대학교 산학협력단 | 잔디경계선에 대한 영상처리를 이용한 잔디깍기 로봇 및 이의 제어 방법 |
US20210255638A1 (en) * | 2020-02-19 | 2021-08-19 | Positec Power Tools (Suzhou) Co., Ltd. | Area Division and Path Forming Method and Apparatus for Self-Moving Device and Automatic Working System |
CN114063609A (zh) * | 2020-07-27 | 2022-02-18 | 河北工业大学 | 智能割草机器人的避障控制方法及控制*** |
CN114881853A (zh) * | 2022-03-24 | 2022-08-09 | 深圳拓邦股份有限公司 | 一种智能割草机局部全景图创建方法、装置、电子设备及存储介质 |
EP4018802A4 (de) * | 2019-10-18 | 2022-11-09 | Nanjing Chervon Industry Co., Ltd. | Autonom fahren rasenmähsystem, autonom fahrender rasenmäher und autonom fahrende vorrichtung für den aussenbereich |
EP4173468A1 (de) * | 2021-10-27 | 2023-05-03 | CNH Industrial Belgium NV | System und verfahren zur steuerung der komponentenposition einer landwirtschaftlichen erntemaschine unter verwendung von bilddaten |
US11797824B2 (en) | 2019-10-29 | 2023-10-24 | Samsung Electronics Co., Ltd. | Electronic apparatus and method for controlling thereof |
US12029156B1 (en) | 2020-01-09 | 2024-07-09 | Euchron, Inc. | System and method for autonomous lawn care |
Families Citing this family (44)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2013671B1 (de) | 2006-03-17 | 2018-04-25 | iRobot Corporation | Rasenpflegeroboter |
EP2885684B1 (de) * | 2012-08-14 | 2018-05-09 | Husqvarna AB | Mäher mit objekterkennungssystem |
US10551851B2 (en) * | 2013-07-01 | 2020-02-04 | Steven Sounyoung Yu | Autonomous unmanned road vehicle for making deliveries |
CN107357287A (zh) * | 2014-01-21 | 2017-11-17 | 宝时得科技(中国)有限公司 | 自动割草机 |
US9804594B2 (en) * | 2014-11-07 | 2017-10-31 | Clearpath Robotics, Inc. | Self-calibrating sensors and actuators for unmanned vehicles |
US9538702B2 (en) * | 2014-12-22 | 2017-01-10 | Irobot Corporation | Robotic mowing of separated lawn areas |
US10777000B2 (en) * | 2014-12-27 | 2020-09-15 | Husqvarna Ab | Garden street view |
US9630319B2 (en) | 2015-03-18 | 2017-04-25 | Irobot Corporation | Localization and mapping using physical features |
KR102314637B1 (ko) * | 2015-03-23 | 2021-10-18 | 엘지전자 주식회사 | 로봇 청소기 및 이를 구비하는 로봇 청소 시스템 |
KR101697857B1 (ko) * | 2015-04-08 | 2017-01-18 | 엘지전자 주식회사 | 이동 로봇 및 그의 위치인식방법 |
US20170090456A1 (en) * | 2015-09-25 | 2017-03-30 | Multimedia Image Solution Limited | Autonomous cleaning robot |
SG11201808223SA (en) | 2015-12-06 | 2018-10-30 | Robotic Lawn Care Sweden Ab | Method and means for mowing lawns |
US10788836B2 (en) * | 2016-02-29 | 2020-09-29 | AI Incorporated | Obstacle recognition method for autonomous robots |
US11172608B2 (en) | 2016-06-30 | 2021-11-16 | Tti (Macao Commercial Offshore) Limited | Autonomous lawn mower and a system for navigating thereof |
US11172605B2 (en) | 2016-06-30 | 2021-11-16 | Tti (Macao Commercial Offshore) Limited | Autonomous lawn mower and a system for navigating thereof |
DK179365B1 (en) * | 2016-11-30 | 2018-05-22 | Agro Intelligence Aps | Saftey system for mowers and mower with such a safety system |
US10430657B2 (en) * | 2016-12-12 | 2019-10-01 | X Development Llc | Object recognition tool |
WO2018142483A1 (ja) | 2017-01-31 | 2018-08-09 | 本田技研工業株式会社 | 無人作業システム、管理サーバー、及び無人作業機 |
CN110199301A (zh) | 2017-01-31 | 2019-09-03 | 本田技研工业株式会社 | 无人作业***、管理服务器以及无人作业机 |
SE540794C2 (en) * | 2017-02-06 | 2018-11-13 | Acconeer Ab | An autonomous mobile robot with radar sensors |
US11582903B1 (en) | 2017-05-17 | 2023-02-21 | Hydro-Gear Limited Partnership | Vision based guidance system and method for lawn mowing devices |
US20190034857A1 (en) | 2017-07-28 | 2019-01-31 | Nuro, Inc. | Food and beverage delivery system on autonomous and semi-autonomous vehicle |
US11197414B2 (en) | 2018-01-26 | 2021-12-14 | Briggs & Stratton, Llc | Systems and devices for autonomous lawn care |
CN111615676B (zh) * | 2018-03-26 | 2023-05-23 | 赫尔实验室有限公司 | 用于估计由监督机器学习器做出的决策的不确定性的***和方法 |
JP6997293B2 (ja) | 2018-03-30 | 2022-01-17 | 本田技研工業株式会社 | 自律走行作業機、及び制御システム |
US11350564B1 (en) * | 2018-06-28 | 2022-06-07 | Hydro-Gear Limited Partnership | Vision system integration |
US11297758B2 (en) | 2018-09-10 | 2022-04-12 | International Business Machines Corporation | Automated leveling system for maintaining level of a surface |
EP3863743A4 (de) * | 2018-10-09 | 2021-12-08 | Resonai Inc. | Systeme und verfahren zur 3d-szenenvergrösserung und -rekonstruktion |
US11547052B1 (en) | 2018-10-10 | 2023-01-10 | Hydro-Gear Limited Partnership | Audible operator feedback for riding lawn mower applications |
DE112018008157T5 (de) * | 2018-11-20 | 2021-08-05 | Honda Motor Co., Ltd. | Steuervorrichtung einer autonom navigierenden Arbeitsmaschine |
US12038752B1 (en) | 2019-01-17 | 2024-07-16 | Renu Robotics Corp. | Autonomous vehicle navigational fallover |
US11464161B1 (en) | 2019-03-29 | 2022-10-11 | Hydro-Gear Limited Partnership | Automatic sensitivity adjustment for an autonomous mower |
US11653593B2 (en) | 2019-08-02 | 2023-05-23 | Embankscape Equipment LLC | Handheld unit with safety features for remote-control slope mowing system |
US11234362B2 (en) | 2019-08-02 | 2022-02-01 | Embankscape Equipment LLC | Remote-control slope mowing system with safety features |
US11240966B2 (en) | 2019-08-02 | 2022-02-08 | Embankscape Equipment LLC | Slope mower with safety features |
CN110471444B (zh) * | 2019-08-19 | 2022-07-12 | 西安微电子技术研究所 | 基于自主学习的无人机智能避障方法 |
KR20190108530A (ko) * | 2019-09-04 | 2019-09-24 | 엘지전자 주식회사 | 이동 로봇 및 그의 구동 방법 |
US11951977B1 (en) | 2019-09-23 | 2024-04-09 | Renu Robotics Corp. | Autonomous vehicle panel and post detection |
KR20210080004A (ko) * | 2019-12-20 | 2021-06-30 | 엘지전자 주식회사 | 로봇 및 그 제어 방법 |
US11618167B2 (en) * | 2019-12-24 | 2023-04-04 | X Development Llc | Pixelwise filterable depth maps for robots |
EP4128100A1 (de) | 2020-03-23 | 2023-02-08 | Nuro, Inc. | Verfahren und vorrichtung für automatisierte lieferungen |
CN114648691A (zh) * | 2020-12-21 | 2022-06-21 | 苏州科瓴精密机械科技有限公司 | 一种障碍物识别方法、装置、设备、介质及除草机器人 |
CN114677582A (zh) * | 2020-12-24 | 2022-06-28 | 苏州科瓴精密机械科技有限公司 | 一种障碍物识别方法、装置、设备、介质及除草机器人 |
US20230320263A1 (en) * | 2022-03-24 | 2023-10-12 | Willand (Beijing) Technology Co., Ltd. | Method for determining information, remote terminal, and mower |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6611738B2 (en) | 1999-07-12 | 2003-08-26 | Bryan J. Ruffner | Multifunctional mobile appliance |
WO2007091967A1 (en) * | 2006-02-07 | 2007-08-16 | Hexagon Metrology Ab | Method for controlling garden or domestic machines, and garden or domestic machine. |
WO2010077198A1 (en) | 2008-12-30 | 2010-07-08 | Husqvarna Ab | An autonomous robotic lawn mower and a method for establishing a wireless communication link between the lawn mower and a user |
US20100324731A1 (en) | 2009-06-18 | 2010-12-23 | Michael Todd Letsky | Method for establishing a desired area of confinement for an autonomous robot and autonomous robot implementing a control system for executing the same |
WO2011002512A1 (en) | 2009-07-01 | 2011-01-06 | Mtd Products Inc | Visual segmentation of lawn grass |
EP2286653A2 (de) | 2009-08-17 | 2011-02-23 | Robert Bosch GmbH | Autonome mobile Plattform zur Oberflächenbearbeitung |
EP2340701A2 (de) * | 2010-01-05 | 2011-07-06 | Deere & Company | Vorrichtung, Verfahren und Computerprogrammprodukt für Schneidelementkontrolle |
EP2342964A1 (de) * | 2010-01-06 | 2011-07-13 | Deere & Company | Adaptive Planung eines Dienstroboters |
EP2428107A1 (de) * | 2010-09-09 | 2012-03-14 | Fabrizio Bernini | Rasenmäher |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE19953739C2 (de) * | 1999-11-09 | 2001-10-11 | Siemens Ag | Einrichtung und Verfahren zur objektorientierten Markierung und Zuordnung von Information zu selektierten technologischen Komponenten |
KR20020008848A (ko) * | 2000-03-31 | 2002-01-31 | 이데이 노부유끼 | 로봇 장치, 로봇 장치의 행동 제어 방법, 외력 검출 장치및 외력 검출 방법 |
JP3529049B2 (ja) * | 2002-03-06 | 2004-05-24 | ソニー株式会社 | 学習装置及び学習方法並びにロボット装置 |
JP3951235B2 (ja) * | 2003-02-19 | 2007-08-01 | ソニー株式会社 | 学習装置及び学習方法並びにロボット装置 |
JP4460528B2 (ja) * | 2004-12-14 | 2010-05-12 | 本田技研工業株式会社 | 識別対象識別装置およびそれを備えたロボット |
US7801330B2 (en) * | 2005-06-24 | 2010-09-21 | Objectvideo, Inc. | Target detection and tracking from video streams |
US7804980B2 (en) * | 2005-08-24 | 2010-09-28 | Denso Corporation | Environment recognition device |
JP4870546B2 (ja) * | 2006-12-27 | 2012-02-08 | 株式会社岩根研究所 | レイヤー生成・選択機能を備えたcvタグ映像表示装置 |
EP1978432B1 (de) * | 2007-04-06 | 2012-03-21 | Honda Motor Co., Ltd. | Routingvorrichtung für eine autonome mobile Einheit |
US8189905B2 (en) * | 2007-07-11 | 2012-05-29 | Behavioral Recognition Systems, Inc. | Cognitive model for a machine-learning engine in a video analysis system |
US8072448B2 (en) * | 2008-01-15 | 2011-12-06 | Google Inc. | Three-dimensional annotations for street view data |
KR101553522B1 (ko) * | 2008-12-29 | 2015-09-16 | 삼성전자 주식회사 | 로봇 및 그 제어 방법 |
US8648702B2 (en) * | 2010-08-20 | 2014-02-11 | Denso International America, Inc. | Combined time-of-flight and image sensor systems |
US8639644B1 (en) * | 2011-05-06 | 2014-01-28 | Google Inc. | Shared robot knowledge base for use with cloud computing system |
US8842163B2 (en) * | 2011-06-07 | 2014-09-23 | International Business Machines Corporation | Estimation of object properties in 3D world |
-
2012
- 2012-07-27 EP EP12178244.5A patent/EP2689650B1/de active Active
-
2013
- 2013-07-26 US US13/951,504 patent/US9137943B2/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6611738B2 (en) | 1999-07-12 | 2003-08-26 | Bryan J. Ruffner | Multifunctional mobile appliance |
WO2007091967A1 (en) * | 2006-02-07 | 2007-08-16 | Hexagon Metrology Ab | Method for controlling garden or domestic machines, and garden or domestic machine. |
WO2010077198A1 (en) | 2008-12-30 | 2010-07-08 | Husqvarna Ab | An autonomous robotic lawn mower and a method for establishing a wireless communication link between the lawn mower and a user |
US20100324731A1 (en) | 2009-06-18 | 2010-12-23 | Michael Todd Letsky | Method for establishing a desired area of confinement for an autonomous robot and autonomous robot implementing a control system for executing the same |
WO2011002512A1 (en) | 2009-07-01 | 2011-01-06 | Mtd Products Inc | Visual segmentation of lawn grass |
EP2286653A2 (de) | 2009-08-17 | 2011-02-23 | Robert Bosch GmbH | Autonome mobile Plattform zur Oberflächenbearbeitung |
EP2340701A2 (de) * | 2010-01-05 | 2011-07-06 | Deere & Company | Vorrichtung, Verfahren und Computerprogrammprodukt für Schneidelementkontrolle |
EP2342964A1 (de) * | 2010-01-06 | 2011-07-13 | Deere & Company | Adaptive Planung eines Dienstroboters |
EP2428107A1 (de) * | 2010-09-09 | 2012-03-14 | Fabrizio Bernini | Rasenmäher |
Cited By (35)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104904404A (zh) * | 2014-03-14 | 2015-09-16 | 宝时得机械(中国)有限公司 | 智能割草机 |
EP2939513A1 (de) * | 2014-04-30 | 2015-11-04 | LG Electronics Inc. | Rasenmäherroboter und Steuerungsverfahren dafür |
DE102014015493B4 (de) | 2014-10-06 | 2019-04-18 | Audi Ag | Verfahren zum Betrieb eines Kraftfahrzeugs und Kraftfahrzeug |
WO2016055159A3 (de) * | 2014-10-11 | 2016-07-14 | Audi Ag | Verfahren zum betrieb eines automatisiert geführten, fahrerlosen kraftfahrzeugs und überwachungssystem |
CN106794874B (zh) * | 2014-10-11 | 2021-05-18 | 奥迪股份公司 | 用于运行自动引导的无人驾驶的机动车的方法和监控*** |
CN106794874A (zh) * | 2014-10-11 | 2017-05-31 | 奥迪股份公司 | 用于运行自动引导的无人驾驶的机动车的方法和监控*** |
DE102014015075B4 (de) | 2014-10-11 | 2019-07-25 | Audi Ag | Verfahren zum Betrieb eines automatisiert geführten, fahrerlosen Kraftfahrzeugs und Überwachungssystem |
US10338598B2 (en) | 2014-10-11 | 2019-07-02 | Audi Ag | Method for operating an automatically driven, driverless motor vehicle and monitoring system |
US10102429B2 (en) | 2014-12-16 | 2018-10-16 | Irobot Corporation | Systems and methods for capturing images and annotating the captured images with information |
EP3234839A4 (de) * | 2014-12-16 | 2018-08-29 | iRobot Corporation | Systeme und verfahren zur bilderfassung und kommentierung des erfassten bildes mit informationen |
CN105922257A (zh) * | 2016-04-28 | 2016-09-07 | 纳博特南京科技有限公司 | 一种基于移动电子设备的机器人示教*** |
EP3298874A1 (de) | 2016-09-22 | 2018-03-28 | Honda Research Institute Europe GmbH | Robotergartenarbeitsvorrichtung und verfahren zur steuerung davon |
US10912253B2 (en) | 2016-09-22 | 2021-02-09 | Honda Research Institute Europe Gmbh | Robotic gardening device and method for controlling the same |
CN107006229A (zh) * | 2017-03-30 | 2017-08-04 | 江苏科技大学 | 一种坐骑式割草机翻滚保护装置及其保护方法 |
IT201800010737A1 (it) * | 2018-11-30 | 2020-05-30 | Volta Robots S R L | Metodo di controllo di un mezzo di lavorazione del terreno sulla base di elaborazioni d’immagini perfezionato e relativo sistema |
WO2020110027A1 (en) * | 2018-11-30 | 2020-06-04 | Volta Robots S.R.L. | An improved method for controlling a soil working means based on image processing and related system |
EP3670109A3 (de) * | 2018-12-18 | 2020-07-15 | Samsung Electronics Co., Ltd. | Verfahren und vorrichtung zur steuerung des verhaltens eines dienstroboters |
US11602854B2 (en) | 2018-12-18 | 2023-03-14 | Samsung Electronics Co., Ltd. | Method and apparatus for controlling behavior of service robot |
IT201800020182A1 (it) * | 2018-12-19 | 2020-06-19 | Fabrizio Bernini | Robot tagliaerba |
EP3673721A1 (de) * | 2018-12-19 | 2020-07-01 | Fabrizio Bernini | Mähroboter |
EP4018802A4 (de) * | 2019-10-18 | 2022-11-09 | Nanjing Chervon Industry Co., Ltd. | Autonom fahren rasenmähsystem, autonom fahrender rasenmäher und autonom fahrende vorrichtung für den aussenbereich |
CN112673799B (zh) * | 2019-10-18 | 2024-06-21 | 南京泉峰科技有限公司 | 自行走割草***和户外行走设备 |
CN112684785A (zh) * | 2019-10-18 | 2021-04-20 | 南京德朔实业有限公司 | 自行走割草***和户外行走设备 |
CN112673799A (zh) * | 2019-10-18 | 2021-04-20 | 南京德朔实业有限公司 | 自行走割草***和户外行走设备 |
GB2588614B (en) * | 2019-10-29 | 2023-01-11 | Samsung Electronics Co Ltd | Method and system for customising a machine learning model |
GB2588614A (en) * | 2019-10-29 | 2021-05-05 | Samsung Electronics Co Ltd | Method and system for customising a machine learning model |
US11797824B2 (en) | 2019-10-29 | 2023-10-24 | Samsung Electronics Co., Ltd. | Electronic apparatus and method for controlling thereof |
KR20210059839A (ko) * | 2019-11-15 | 2021-05-26 | 동의대학교 산학협력단 | 잔디경계선에 대한 영상처리를 이용한 잔디깍기 로봇 및 이의 제어 방법 |
US12029156B1 (en) | 2020-01-09 | 2024-07-09 | Euchron, Inc. | System and method for autonomous lawn care |
US20210255638A1 (en) * | 2020-02-19 | 2021-08-19 | Positec Power Tools (Suzhou) Co., Ltd. | Area Division and Path Forming Method and Apparatus for Self-Moving Device and Automatic Working System |
CN114063609A (zh) * | 2020-07-27 | 2022-02-18 | 河北工业大学 | 智能割草机器人的避障控制方法及控制*** |
CN112659124A (zh) * | 2020-12-14 | 2021-04-16 | 南昌大学 | 一种基于Android***的虚拟仿真与控制*** |
CN112818806A (zh) * | 2021-01-27 | 2021-05-18 | 国网四川省电力公司电力科学研究院 | 一种基于深度学习的变电站巡检机器人辅助导航方法 |
EP4173468A1 (de) * | 2021-10-27 | 2023-05-03 | CNH Industrial Belgium NV | System und verfahren zur steuerung der komponentenposition einer landwirtschaftlichen erntemaschine unter verwendung von bilddaten |
CN114881853A (zh) * | 2022-03-24 | 2022-08-09 | 深圳拓邦股份有限公司 | 一种智能割草机局部全景图创建方法、装置、电子设备及存储介质 |
Also Published As
Publication number | Publication date |
---|---|
US9137943B2 (en) | 2015-09-22 |
EP2689650B1 (de) | 2014-09-10 |
US20140032033A1 (en) | 2014-01-30 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP2689650B1 (de) | Lernender autonomer Rasenmäher | |
US11672193B2 (en) | Method for the operation of a self-propelled agricultural working machine | |
JP6949988B2 (ja) | 領域特定方法、装置、記憶媒体及びプロセッサ | |
EP2885684B1 (de) | Mäher mit objekterkennungssystem | |
US9497901B2 (en) | Boundary definition system for a robotic vehicle | |
US20180255704A1 (en) | Zone control system for a robotic vehicle | |
EP3237984B1 (de) | Bereichsausschluss für den betrieb eines roboterfahrzeugs | |
CN110612492A (zh) | 一种自驱动无人驾驶割草机 | |
KR102347511B1 (ko) | 잔디경계선에 대한 영상처리를 이용한 잔디깍기 로봇 및 이의 제어 방법 | |
EP3686704B1 (de) | VERFAHREN ZUM ERZEUGEN EINER DARSTELLUNG UND SYSTEM ZUM
EINLERNEN EINER AUTONOMEN VORRICHTUNG ZUM BETRIEB AUF DER
GRUNDLAGE DIESER DARSTELLUNG | |
US20210137097A1 (en) | System and methods for automated wildlife detection, monitoring and control | |
US20210364315A1 (en) | Route management system and management method thereof | |
US11882787B1 (en) | Automatic sensitivity adjustment for an autonomous mower | |
CN110238837B (zh) | 自主移动装置、自主移动方法以及存储介质 | |
WO2016097897A1 (en) | Robotic patrol vehicle | |
JP6704979B1 (ja) | 無人飛行装置、無人飛行システム及び無人飛行装置制御システム | |
CN110662417A (zh) | 农作业装置、农作业管理***以及程序 | |
WO2022079172A1 (en) | Treatment system for plant specific treatment | |
US20180016006A1 (en) | Smart unmanned aerial vehicle for home | |
CN115167427A (zh) | 一种视觉障碍物识别方法、***及割草机器人 | |
CN114973573A (zh) | 目标入侵确定方法、装置、存储介质及电子装置 | |
CN110209154B (zh) | 自动收割机的残留收割路径规划***及其方法 | |
EP3673721B1 (de) | Mähroboter | |
WO2022079176A1 (en) | Treatment system for weed specific treatment | |
US20240206455A1 (en) | Weed control with an autonomous work device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PUAI | Public reference made under article 153(3) epc to a published international application that has entered the european phase |
Free format text: ORIGINAL CODE: 0009012 |
|
17P | Request for examination filed |
Effective date: 20130131 |
|
AK | Designated contracting states |
Kind code of ref document: A1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
AX | Request for extension of the european patent |
Extension state: BA ME |
|
RIC1 | Information provided on ipc code assigned before grant |
Ipc: A01D 34/00 20060101AFI20140217BHEP |
|
GRAP | Despatch of communication of intention to grant a patent |
Free format text: ORIGINAL CODE: EPIDOSNIGR1 |
|
INTG | Intention to grant announced |
Effective date: 20140509 |
|
RIN1 | Information on inventor provided before grant (corrected) |
Inventor name: WERSING, DR. HEIKO Inventor name: EINECKE, NILS Inventor name: FRANZIUS, DR. MATHIAS |
|
GRAS | Grant fee paid |
Free format text: ORIGINAL CODE: EPIDOSNIGR3 |
|
GRAA | (expected) grant |
Free format text: ORIGINAL CODE: 0009210 |
|
AK | Designated contracting states |
Kind code of ref document: B1 Designated state(s): AL AT BE BG CH CY CZ DE DK EE ES FI FR GB GR HR HU IE IS IT LI LT LU LV MC MK MT NL NO PL PT RO RS SE SI SK SM TR |
|
REG | Reference to a national code |
Ref country code: GB Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: EP |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: FG4D |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: REF Ref document number: 686181 Country of ref document: AT Kind code of ref document: T Effective date: 20141015 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R096 Ref document number: 602012003042 Country of ref document: DE Effective date: 20141023 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: ES Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: LT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: NO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20141210 Ref country code: SE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: FI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: GR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20141211 |
|
REG | Reference to a national code |
Ref country code: NL Ref legal event code: VDEP Effective date: 20140910 |
|
REG | Reference to a national code |
Ref country code: LT Ref legal event code: MG4D |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LV Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: RS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: CY Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: HR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
REG | Reference to a national code |
Ref country code: AT Ref legal event code: MK05 Ref document number: 686181 Country of ref document: AT Kind code of ref document: T Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: NL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: PT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20150112 Ref country code: CZ Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: SK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: RO Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: IS Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20150110 Ref country code: EE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: PL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: AT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R097 Ref document number: 602012003042 Country of ref document: DE |
|
PLBE | No opposition filed within time limit |
Free format text: ORIGINAL CODE: 0009261 |
|
STAA | Information on the status of an ep patent application or granted ep patent |
Free format text: STATUS: NO OPPOSITION FILED WITHIN TIME LIMIT |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: DK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
26N | No opposition filed |
Effective date: 20150611 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: IT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: SI Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MC Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
REG | Reference to a national code |
Ref country code: CH Ref legal event code: PL |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: LU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20150727 |
|
REG | Reference to a national code |
Ref country code: IE Ref legal event code: MM4A |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: CH Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20150731 Ref country code: LI Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20150731 |
|
REG | Reference to a national code |
Ref country code: FR Ref legal event code: ST Effective date: 20160331 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: FR Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20150731 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: BE Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: IE Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20150727 |
|
GBPC | Gb: european patent ceased through non-payment of renewal fee |
Effective date: 20160727 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: MT Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: GB Free format text: LAPSE BECAUSE OF NON-PAYMENT OF DUE FEES Effective date: 20160727 Ref country code: HU Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT; INVALID AB INITIO Effective date: 20120727 Ref country code: BG Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: SM Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: TR Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 Ref country code: MK Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
PG25 | Lapsed in a contracting state [announced via postgrant information from national office to epo] |
Ref country code: AL Free format text: LAPSE BECAUSE OF FAILURE TO SUBMIT A TRANSLATION OF THE DESCRIPTION OR TO PAY THE FEE WITHIN THE PRESCRIBED TIME-LIMIT Effective date: 20140910 |
|
REG | Reference to a national code |
Ref country code: DE Ref legal event code: R084 Ref document number: 602012003042 Country of ref document: DE |
|
PGFP | Annual fee paid to national office [announced via postgrant information from national office to epo] |
Ref country code: DE Payment date: 20230719 Year of fee payment: 12 |